Aratako

Irodori-TTS. A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

T5Gemma-TTS. Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

MioTTS-Inference. Inference server for MioTTS, a lightweight and fast LLM-based TTS model.

Irodori-TTS-Server. OpenAI Text-to-Speech API compatible server for Irodori-TTS

MioCodec. Python

Japanese-RP-Bench. Jupyter Notebook

CALM-DACVAE. An attempt to reproduce CALM (Continuous Audio Language Models) using DACVAE as the audio VAE.

Task-Vector-Merge-Optimzier. Python

magpie-nemotron. Magpieという手法とNemotron-4-340B-Instructを用いて合成対話データセットを作るコード

llasa-server. シンプルなLlasaの推論サーバー

mergekit-qwen2. Tools for merging pretrained large language models.